Sidekick Ai

• Outcome: Review
• Latest audit: May 29, 2026 at 9:37 PM UTC
• Version:
  1.0.2

Overview

This is a coherent Sidekick AI integration, but it gives an agent broad authenticated access to run actions and raw API requests without clear guardrails for sensitive or destructive operations.

Install only if you are comfortable granting Membrane-mediated access to your Sidekick AI account. Before use, tell the agent to confirm any create, update, delete, or raw proxy request, and avoid including secrets or unrelated private context in request paths, headers, query parameters, or bodies.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill explicitly documents raw proxy requests to an external API but does not warn that request paths, query parameters, headers, or bodies may contain sensitive user or system data that will be transmitted off-platform. In an agent setting, this increases the risk of unreviewed exfiltration of personal, organizational, or conversation-derived data to the external service.

VirusTotal

63/63 vendors flagged this skill as clean.